Title Details

Lecturer at the GERiiCO laboratory at University Lille 3, Gerald Kembellec specializes in information science and communication.

Professor of Documentary Engineering Chair of CNAM, Ghislaine Chartron is director of the National Institute of Science and Technical documentation.

Professor at the University Paris 8, Imad Saleh is the Paragraph laboratory director and director of the graduate school Cognition Language Interaction.

PREFACE xi
Gérald KEMBELLEC, Ghislaine CHARTRON and Imad SALEH

CHAPTER 1. GENERAL INTRODUCTION TO RECOMMENDER SYSTEMS 1
Ghislaine CHARTRON and Gérald KEMBELLEC

1.1. Putting it into perspective 1

1.2. An interdisciplinary subject 2

1.3. The fundamentals of algorithms 4

1.3.1. Collaborative filtering 4

1.3.2. Content filtering 7

1.3.3. Hybrid methods 9

1.3.4. Conclusion on historical recommendation models 11

1.4. Content offers and recommender systems 11

1.4.1. Culture and recommender systems 11

1.4.2. Recommender systems and the e-commerce of content 16

1.4.3. The behavior of users 18

1.5. Current issues 19

1.6. Bibliography 19

CHAPTER 2. UNDERSTANDING USERS’ EXPECTATIONS FOR RECOMMENDER SYSTEMS: THE CASE OF SOCIAL MEDIA 25
Jean-Claude DOMENGET and Alexandre COUTANT

2.1. Introduction: the omnipresence of recommender systems 25

2.2. The social approach to prescription 27

2.2.1. The theory of the prescription and online interactions 27

2.2.2. Conditions for recognition of the prescription 29

2.2.3. The specificities of social media 30

2.3. Users who do not focus on the prescriptions of platforms 31

2.3.1. Facebook: the link, the type of activity and the context 32

2.3.2. Twitter: prescription between peers and explanation of prescription 38

2.3.3. Conditions for the recognition of a prescription: announcement and enunciation 44

2.4. A guide for considering recommender systems adapted to different forms of social media 45

2.5. Conclusion 48

2.6. Bibliography 49

CHAPTER 3. RECOMMENDER SYSTEMS AND SOCIAL NETWORKS: WHAT ARE THE IMPLICATIONS FOR DIGITAL MARKETING? 53
Maria MERCANTI-GUÉRIN

3.1. Social recommendations: an ancient practice revived by the digital age 54

3.1.1. Recommendations: a difficult management for brands 55

3.1.2. Internet recommendations: social presence and personalized recommendations 55

3.2. Social recommendations: how are they used for e-commerce? 58

3.2.1. Efficiency of recommender systems with regard to the performance of e-commerce websites 58

3.2.2. Recommender systems used by social networks: from e-commerce to social commerce 59

3.3. Conclusion 66

3.4. Bibliography 68

CHAPTER 4. RECOMMENDER SYSTEMS AND DIVERSITY: TAKING ADVANTAGE OF THE LONG TAIL AND THE DIVERSITY OF RECOMMENDATION LISTS 71
Muriel FOULONNEAU, Valentin GROUÈS, Yannick NAUDET and Max CHEVALIER

4.1. The stakes associated with diversity within recommender systems 72

4.1.1. Individual diversity or the individual perception of diversity 73

4.1.2. The stakes and impacts of aggregate diversity 74

4.2. Recommendation algorithms and diversity: trends, evaluation and optimization 77

4.2.1. The tendency for recommendation algorithms to focus on the head 78

4.2.2. The evaluation of diversity in recommender systems 80

4.2.3. Recommendation algorithms which favor individual diversity 81

4.2.4. Recommendation algorithms which favor aggregate diversity 81

4.2.5. The shift toward user-centered diversity approaches 82

4.3. Conclusion and new directions 85

4.4. Bibliography 87

CHAPTER 5. ISONTRE: INTELLIGENT TRANSFORMER OF SOCIAL NETWORKS INTO A RECOMMENDATION ENGINE ENVIRONMENT 93
Rana CHAMSI ABU QUBA, Salima HASSAS, Usama FAYYAD, Hammam CHAMSI and Christine GERTOSIO

5.1. Summary 93

5.2. Introduction 94

5.3. Latest developments, definition and history 97

5.3.1. Collaborative filtering techniques 97

5.3.2. General use social networks: what do they contain? 97

5.3.3. Social recommendation 99

5.3.4. The recommendation of concepts 100

5.4. iSoNTRE 101

5.4.1. iSoNTRE: transformer of social networks 102

5.4.2. iSoNTRE: the core of recommendation 107

5.5. Experiments 110

5.5.1. The preparation of data 110

5.5.2. Testing methodology 110

5.5.3. The creation of avatars 111

5.5.4. Results 112

5.5.5. Discussion 113

5.6. Conclusion 114

5.7. Bibliography 115

CHAPTER 6. A TWO-LEVEL RECOMMENDATION APPROACH FOR DOCUMENT SEARCH 119
Manel HMIMIDA and Rushed KANAWATI

6.1. Introduction 119

6.2. Tag recommendation: a brief state of the art 120

6.3. The hypertagging system 122

6.3.1. Metadata 122

6.3.2. Architecture 123

6.4. Recommendation approach 124

6.4.1. Presentation 124

6.4.2. Recommendation algorithm 126

6.5. Evaluation 127

6.5.1. Generation of facets 127

6.5.2. Generation of association rules 129

6.5.3. Evaluation of recommendation rules 130

6.6. Conclusion 131

6.7. Bibliography 132

CHAPTER 7. COMBINING CONFIGURATION AND RECOMMENDATION TO ENABLE AN INTERACTIVE GUIDANCE OF PRODUCT LINE CONFIGURATION 135
Raouia TRIKI , Raúl MAZO and Camille SALINESI

7.1. Introduction 135

7.2. Context 137

7.2.1. Configuration 137

7.2.2. Recommendation 139

7.2.3. Obstacles and challenges of interactive PL configuration 141

7.3. Overview of the proposed approach 142

7.4. Preliminary evaluation 148

7.5. Discussion and related work 148

7.5.1. Recommendation techniques 148

7.6. Conclusion and future work 151

7.7. Bibliography 151

CHAPTER 8. SEMIO-COGNITIVE SPACES: THE FRONTIER OF RECOMMENDER SYSTEMS 157
Hakim HACHOUR, Samuel SZONIECKY and Safia ABOUAD

8.1. Introduction 157

8.2. Latest developments: finalized activities, recommender systems and the relevance of information 159

8.2.1. Cognitive dynamics of finalized activities 159

8.2.2. The foundations of recommender systems 161

8.2.3. What information relevance? 166

8.3. Observable interests for decision theory: a combination of content-based, collaboration based and knowledge-based recommendations 169

8.3.1. Methodology: meta-analysis and modeling of the process 169

8.3.2. Analysis and modeling of a macro-process for responding to a call for R&D projects 171

8.3.3. Analysis and model of a socio-organizational tool for the management of customer complaints 173

8.4. Discussion and conclusions 177

8.4.1. Discussion: the performance of the filtering methods and semio-cognitive criteria for relevance 177

8.5. Conclusions: recommender systems linked to finalized activities 181

8.5.1. The localization of activities and geographical information systems: a new kind of data 182

8.5.2. Transparency of the use of personal data, data protection and ownership 183

8.6. Acknowledgments 185

8.7. Bibliography 185

CHAPTER 9. THE FRENCH-SPEAKING LITERARY PRESCRIPTION MARKET IN NETWORKS 191
Louis WIART

9.1. Introduction 191

9.2. The economy of prescription 193

9.2.1. The notion of prescription 193

9.2.2. From the advisors market to the prescription market 194

9.3. Methodology 196

9.4. The competitive structure of the market of online social networks of readers 197

9.4.1. Pure player networks and the audience strategy 199

9.4.2. Amateur networks and the survival strategy 201

9.4.3. Backed networks and the hybridization strategy 202

9.5. The organization of prescription 204

9.5.1. Social prescription 205

9.5.2. Editorial prescription 206

9.5.3. Algorithmic prescription 207

9.6. Conclusion: what legitimacy for literary prescription? 208

9.7. Appendix: list of interviews undertaken 210

9.8. Bibliography 210

CHAPTER 10. PRESENTATION OF OFFERED SERVICES: BABELIO, A RECOMMENDATION ENGINE DEDICATED TO BOOKS 213
Vassil STEFANOV, Guillaume TEISSEIRE and Pierre FRÉMAUX

10.1. Introduction 213

10.2. The problem of qualitative pertinence 216

10.3. The problem of quantitative pertinence 217

10.4. Balancing recall and precision 217

10.5. The issue of sparse data 218

10.6. Performance and scalability 218

10.7. A few issues specific to books 219

CHAPTER 11. PRESENTATION OF THE OFFER OF SERVICES: NOMAO, RECOMMENDER SYSTEMS AND INFORMATION SEARCH 221
Estelle DELPECH, Laurent CANDILLIER and Étienne CHAI

11.1. Introduction: the actors of Internet recommendation 221

11.2. Approaches to recommendation 222

11.3. Nomao: a local outlets search and recommendation engine 223

11.3.1. Popularity score 223

11.3.2. Affinity score 224

11.3.3. Social recommendation 225

11.4. Prospects: the move toward interactive recommender systems 225

11.5. Appendix 226

LIST OF AUTHORS 227

INDEX 231